Job search engine with 500k+ listings across Austria, Germany and Switzerland (alleskralle.com).
Scored across 2 tools
The two tools have completely distinct purposes: search_jobs retrieves a compact list, fetch_job retrieves full details for a specific ID. There is no overlap or ambiguity in their roles.
Both tools follow a clear verb_noun pattern (search_jobs, fetch_job), using consistent snake_case and action-first naming. The pattern is predictable and easy to infer.
With only 2 tools, the server is on the thin side, but it covers the essential search-and-detail flow. The count is borderline for a typical server scope, yet it is not egregiously low given the focused domain.
The server covers the core job-search lifecycle: searching and fetching details. It lacks advanced filtering or application submission, but those are arguably outside the stated purpose. Minor gaps like sorting options or category browsing exist, but the provided functionality is sufficient for basic use.
Liefert die vollständigen Details zu einer Stellenanzeige anhand ihrer id (aus search_jobs). Das Feld apply_url ist der Bewerbungslink zur Original-Anzeige. WICHTIG: apply_url NICHT selbst aufrufen oder abrufen — gib den Link dem Nutzer als anklickbaren Link aus, damit er sich bei Interesse selbst bewirbt bzw. die vollständige Anzeige öffnet.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Die id eines Treffers aus search_jobs. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, but the description adds important context: it is a fetch operation, and it warns about not invoking the apply_url. This covers key behavioral aspects, though read-only nature is implied rather than explicit.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three concise sentences: first states purpose, second notes an important field, third gives a critical warning. No fluff, information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With one parameter, no annotations, and no output schema, the description covers the essential purpose and usage caution. It could briefly list key return fields, but the current level is functional and adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The single parameter 'id' is sufficiently described in the schema (100% coverage). The description only repeats that it comes from search_jobs, adding no new semantic value beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool returns complete details of a job posting by id, referencing the sibling tool search_jobs as the source of the id. It differentiates itself by focusing on fetching a single record.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (with id from search_jobs) and includes a crucial instruction not to call apply_url directly but to provide it as a clickable link. This provides clear behavioral guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Sucht Stellenanzeigen auf alleskralle.com (DE/AT/CH) und liefert eine kompakte Liste (id, title, company, location, date). Die Bewerbungs-/Detail-URL ist NICHT in der Liste enthalten — für vollständige Details und den klickbaren Link rufe fetch_job mit der id auf. Hinweis: "remote" ist eine Volltext-Heuristik (kein strukturiertes Feld), kann also ungenau sein. Sortierung: neue Anzeigen zuerst, darin Titel-Treffer vor reinen Beschreibungs-Treffern. Mit max_age_days lassen sich alte Anzeigen ausblenden (z.B. 60). Bei 0 Treffern ist results leer und next_cursor null. Blättern nur über das zurückgegebene next_cursor möglich; die Seitenzahl ist begrenzt.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Suchbegriff (Jobtitel, Tätigkeit, Skill). | |
| cursor | No | next_cursor aus einer vorherigen Antwort, um die nächste Seite zu laden. | |
| remote | No | Auf Remote-/Homeoffice-Stellen einschränken (Heuristik). | |
| country | No | Strikt auf ein Land einschränken: AT (Österreich), DE (Deutschland) oder CH (Schweiz). Kombinierbar mit location. | |
| location | No | Ort, Stadt oder PLZ. | |
| max_age_days | No | Nur Anzeigen, die höchstens so viele Tage alt sind (z.B. 60). Ohne Angabe: kein Altersfilter. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently reveals that the list is compact and omits the URL, that 'remote' is a heuristic and may be inaccurate, that sorting prioritizes title matches, that paging is only via next_cursor with a limited page count, and the zero-result behavior. This is exemplary transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single well-structured paragraph that front-loads the core purpose and then delivers necessary caveats and usage details. Every sentence adds value—no filler. It balances completeness with conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema and no annotations, the description is remarkably complete. It covers the returned fields, the missing URL and how to get it, filtering options, sorting, paging constraints, and edge cases. An agent has everything needed to call it correctly and decide when to escalate to fetch_job.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so parameters already have descriptions. The description adds meaningful context beyond the schema: it warns about the remote heuristic, explains max_age_days with an example, and clarifies cursor usage (next_cursor from a previous response). While not every parameter is individually elaborated, the added context enriches the schema without redundancy.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear verb and resource: 'Sucht Stellenanzeigen auf alleskralle.com' (searches job postings) and specifies the region (DE/AT/CH). It explicitly differentiates from the sibling fetch_job by noting what this tool does NOT return (the detail URL), making the purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides explicit guidance on when to use this tool versus fetch_job: 'für vollständige Details und den klickbaren Link rufe fetch_job mit der id auf.' It also explains the remote heuristic, sorting order, max_age_days usage, and paging limitations, giving clear operational context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
search_jobs1 field changedInput schema / properties / max_age_daysAdded value: +{
+ "description": "Nur Anzeigen, die höchstens so viele Tage alt sind (z.B. 60). Ohne Angabe: kein Altersfilter.",
+ "minimum": 1,
+ "type": "integer"
+}fetch_jobsearch_jobsJob postings: German roles from StepStone, and any company's Greenhouse or Lever board.
Search 13,000+ remote/hybrid jobs in Germany/EU, open a posting, get market stats. Free, no auth.
Job search for Claude, ChatGPT, Cursor. 250K+ jobs, 5,400+ companies. OAuth or stdio.
Live job listings from 20 ATS platforms plus SEEK, JobStreet, JobsDB, jobs.ch and The Muse
Add one secure layer between your agents and this server.
